{"id":"https://openalex.org/W3186035148","doi":"https://doi.org/10.1109/access.2021.3099071","title":"A Robust Approach for Continuous Interactive Actor-Critic Algorithms","display_name":"A Robust Approach for Continuous Interactive Actor-Critic Algorithms","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3186035148","doi":"https://doi.org/10.1109/access.2021.3099071","mag":"3186035148"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3099071","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3099071","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09493212.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09493212.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047544916","display_name":"Cristian Mill\u00e1n-Arias","orcid":"https://orcid.org/0000-0002-5286-3751"},"institutions":[{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Cristian C. Millan-Arias","raw_affiliation_strings":["Escola Polit\u00e9cnica de Pernambuco, Universidade de Pernambuco, Recife, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-5286-3751","affiliations":[{"raw_affiliation_string":"Escola Polit\u00e9cnica de Pernambuco, Universidade de Pernambuco, Recife, Brazil","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059739611","display_name":"Bruno Fernandes","orcid":"https://orcid.org/0000-0002-6001-3925"},"institutions":[{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno J. T. Fernandes","raw_affiliation_strings":["Escola Polit\u00e9cnica de Pernambuco, Universidade de Pernambuco, Recife, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-6001-3925","affiliations":[{"raw_affiliation_string":"Escola Polit\u00e9cnica de Pernambuco, Universidade de Pernambuco, Recife, Brazil","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044098673","display_name":"Francisco Cruz","orcid":"https://orcid.org/0000-0002-1131-3382"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]},{"id":"https://openalex.org/I4210156023","display_name":"Universidad Central de Chile","ror":"https://ror.org/0577avk88","country_code":"CL","type":"education","lineage":["https://openalex.org/I4210156023"]}],"countries":["AU","CL"],"is_corresponding":false,"raw_author_name":"Francisco Cruz","raw_affiliation_strings":["Escuela de Ingenier\u00eda, Universidad Central de Chile, Santiago, Chile","School of Information Technology, Deakin University, Geelong, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1131-3382","affiliations":[{"raw_affiliation_string":"Escuela de Ingenier\u00eda, Universidad Central de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I4210156023"]},{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032749222","display_name":"Richard Dazeley","orcid":"https://orcid.org/0000-0002-6199-9685"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Richard Dazeley","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6199-9685","affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102941027","display_name":"S\u00e9rgio Fernandes","orcid":"https://orcid.org/0000-0002-5922-4119"},"institutions":[{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Sergio Fernandes","raw_affiliation_strings":["Escola Polit\u00e9cnica de Pernambuco, Universidade de Pernambuco, Recife, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-5922-4119","affiliations":[{"raw_affiliation_string":"Escola Polit\u00e9cnica de Pernambuco, Universidade de Pernambuco, Recife, Brazil","institution_ids":["https://openalex.org/I71437568"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.6681,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9124345,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"104242","last_page":"104260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9628000259399414,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9508000016212463,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.922231912612915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8429229259490967},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7757265567779541},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5139316916465759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5013129711151123},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49831414222717285},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45452937483787537},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.4539194107055664},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43308353424072266},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41703149676322937},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.41472500562667847},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4130682945251465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34785592555999756},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10397395491600037}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.922231912612915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429229259490967},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7757265567779541},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5139316916465759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013129711151123},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49831414222717285},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45452937483787537},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.4539194107055664},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43308353424072266},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41703149676322937},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.41472500562667847},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4130682945251465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34785592555999756},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10397395491600037},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2021.3099071","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3099071","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09493212.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5d8c9207e5434d8f855f4be7660ddbe6","is_oa":true,"landing_page_url":"https://doaj.org/article/5d8c9207e5434d8f855f4be7660ddbe6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 104242-104260 (2021)","raw_type":"article"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30154443","is_oa":false,"landing_page_url":"http://doi.org/10.1109/ACCESS.2021.3099071","pdf_url":null,"source":{"id":"https://openalex.org/S4306401102","display_name":"Own your potential (DEAKIN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:figshare.com:article/20651976","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/A_Robust_Approach_for_Continuous_Interactive_Actor-Critic_Algorithms/20651976","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3099071","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3099071","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09493212.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G29316538","display_name":null,"funder_award_id":"(Code 001)","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G4555147040","display_name":null,"funder_award_id":"432818/2018-9","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G6808181761","display_name":null,"funder_award_id":"432818/2018-9","funder_id":"https://openalex.org/F4320323678","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Ci\u00eancia e Tecnologia do Estado de Pernambuco"},{"id":"https://openalex.org/G8369094086","display_name":null,"funder_award_id":"CIP2018009","funder_id":"https://openalex.org/F4320323458","funder_display_name":"Universidad de Chile"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320323458","display_name":"Universidad de Chile","ror":"https://ror.org/047gc3g35"},{"id":"https://openalex.org/F4320323678","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Ci\u00eancia e Tecnologia do Estado de Pernambuco","ror":"https://ror.org/02te5rf52"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3186035148.pdf","grobid_xml":"https://content.openalex.org/works/W3186035148.grobid-xml"},"referenced_works_count":87,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W50296447","https://openalex.org/W121023703","https://openalex.org/W162622153","https://openalex.org/W264301034","https://openalex.org/W309123013","https://openalex.org/W651043939","https://openalex.org/W1520048352","https://openalex.org/W1543217731","https://openalex.org/W1552401333","https://openalex.org/W1591803298","https://openalex.org/W1770312810","https://openalex.org/W1777239053","https://openalex.org/W1966086707","https://openalex.org/W1966259872","https://openalex.org/W2022057856","https://openalex.org/W2024390895","https://openalex.org/W2058755553","https://openalex.org/W2066237013","https://openalex.org/W2082511574","https://openalex.org/W2089434629","https://openalex.org/W2091565802","https://openalex.org/W2094387729","https://openalex.org/W2098441518","https://openalex.org/W2101539915","https://openalex.org/W2104308387","https://openalex.org/W2105078254","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2153120627","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2156869222","https://openalex.org/W2165150801","https://openalex.org/W2334782222","https://openalex.org/W2400915889","https://openalex.org/W2495235750","https://openalex.org/W2559960928","https://openalex.org/W2737668828","https://openalex.org/W2764902300","https://openalex.org/W2775408020","https://openalex.org/W2781726626","https://openalex.org/W2791797404","https://openalex.org/W2792217087","https://openalex.org/W2793020180","https://openalex.org/W2795786572","https://openalex.org/W2901974609","https://openalex.org/W2904246096","https://openalex.org/W2912947802","https://openalex.org/W2954718200","https://openalex.org/W2957624498","https://openalex.org/W2975684468","https://openalex.org/W3011120880","https://openalex.org/W3012983342","https://openalex.org/W3038676770","https://openalex.org/W3087055389","https://openalex.org/W3096621767","https://openalex.org/W3101926919","https://openalex.org/W3112186687","https://openalex.org/W3139377883","https://openalex.org/W3200372272","https://openalex.org/W4213251304","https://openalex.org/W4214717370","https://openalex.org/W4230557482","https://openalex.org/W4302570325","https://openalex.org/W6602038105","https://openalex.org/W6604963999","https://openalex.org/W6610977167","https://openalex.org/W6635327058","https://openalex.org/W6637840108","https://openalex.org/W6638088447","https://openalex.org/W6674812091","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6713372117","https://openalex.org/W6747473740","https://openalex.org/W6757592117","https://openalex.org/W6764769363","https://openalex.org/W6775311050","https://openalex.org/W6775686901","https://openalex.org/W6780559895","https://openalex.org/W6781344486","https://openalex.org/W6782225252","https://openalex.org/W6792155000","https://openalex.org/W6801402720"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,6,97,196],"refers":[2],"to":[3,16,19,49,77,149,162,185],"a":[4,21,43,83,100,120,123,143,168],"machine":[5],"paradigm":[7],"in":[8,82,99,122,133,167,187],"which":[9],"an":[10,58,91,117,160],"agent":[11,41,63,76,118,161],"interacts":[12],"with":[13,179],"the":[14,26,40,62,75,79,108,111,114,134,138,156,164,188,191],"environment":[15,27,125,148,192],"learn":[17,64,78],"how":[18],"perform":[20],"task.":[22],"The":[23],"characteristics":[24,189],"of":[25,113,137,190],"may":[28],"change":[29],"over":[30],"time":[31],"or":[32],"be":[33],"affected":[34],"by":[35],"disturbances":[36],"not":[37],"controlled,":[38],"avoiding":[39],"finding":[42],"proper":[44],"policy.":[45],"Some":[46],"approaches":[47],"attempt":[48],"address":[50],"these":[51],"problems,":[52],"as":[53,70],"interactive":[54,95,194],"reinforcement":[55,72,96,195],"learning,":[56,73],"where":[57,103],"external":[59],"entity":[60],"helps":[61],"through":[65],"advice.":[66,128],"Other":[67],"approaches,":[68],"such":[69],"robust":[71],"allow":[74],"task,":[80],"acting":[81],"disturbed":[84,124],"environment.":[85,115],"In":[86],"this":[87],"paper,":[88],"we":[89],"propose":[90],"approach":[92,132,158,181],"that":[93,155],"addresses":[94],"problems":[98],"dynamic":[101,135,147],"environment,":[102],"advice":[104],"provides":[105],"information":[106],"on":[107],"task":[109,141,165],"and":[110,142],"dynamics":[112],"Thus,":[116],"learns":[119],"policy":[121],"while":[126],"receiving":[127],"We":[129],"implement":[130],"our":[131,180],"version":[136],"cart-pole":[139],"balancing":[140],"simulated":[144],"robotic":[145],"arm":[146],"organize":[150],"objects.":[151],"Our":[152],"results":[153,175],"show":[154],"proposed":[157],"allows":[159],"complete":[163],"satisfactorily":[166],"dynamic,":[169],"continuous":[170],"state-action":[171],"domain.":[172],"Moreover,":[173],"experimental":[174],"suggest":[176],"agents":[177],"trained":[178],"are":[182],"less":[183],"sensitive":[184],"changes":[186],"than":[193],"agents.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}
